Merge pull request 'fix: [nomad-step-1] S1.1 — add nomad/jobs/forgejo.hcl (service job, host_volume, port 3000) (#840)' (#844) from fix/issue-840 into main

.woodpecker/nomad-validate.yml

@@ -15,9 +15,10 @@
 #
 # Steps (all fail-closed — any error blocks merge):
 #   1. nomad-config-validate  — `nomad config validate` on server + client HCL
-#   2. vault-operator-diagnose — `vault operator diagnose` syntax check on vault.hcl
+#   2. nomad-job-validate      — `nomad job validate` on every nomad/jobs/*.nomad.hcl
-#   3. shellcheck-nomad        — shellcheck the cluster-up + install scripts + disinto
+#   3. vault-operator-diagnose — `vault operator diagnose` syntax check on vault.hcl
-#   4. bats-init-nomad         — `disinto init --backend=nomad --dry-run` smoke tests
+#   4. shellcheck-nomad        — shellcheck the cluster-up + install scripts + disinto
+#   5. bats-init-nomad         — `disinto init --backend=nomad --dry-run` smoke tests
 #
 # Pinned image versions match lib/init/nomad/install.sh (nomad 1.9.5 /
 # vault 1.18.5). Bump there AND here together — drift = CI passing on
@@ -56,7 +57,24 @@ steps:
     commands:
       - nomad config validate nomad/server.hcl nomad/client.hcl
 
-  # ── 2. Vault HCL syntax check ────────────────────────────────────────────
+  # ── 2. Nomad jobspec HCL syntax check ────────────────────────────────────
+  # `nomad job validate` is a *different* tool from `nomad config validate` —
+  # the former parses jobspec HCL (job/group/task blocks, driver config,
+  # volume refs, network ports), the latter parses agent config HCL
+  # (server/client blocks). Running step 1 on a jobspec would reject it
+  # with "unknown block 'job'", and vice versa. Hence two separate steps.
+  #
+  # Validation is offline: no running Nomad server is required (exit 0 on
+  # valid HCL, 1 on syntax/semantic error). One invocation per file — the
+  # CLI takes a single path argument. New jobspecs get explicit lines here
+  # so bringing one up is a conscious CI edit, matching step 1's pattern
+  # and this file's "no-ad-hoc-steps" principle.
+  - name: nomad-job-validate
+    image: hashicorp/nomad:1.9.5
+    commands:
+      - nomad job validate nomad/jobs/forgejo.nomad.hcl
+
+  # ── 3. Vault HCL syntax check ────────────────────────────────────────────
   # `vault operator diagnose` loads the config and runs a suite of checks.
   # Exit codes:
   #   0 — all checks green
@@ -81,7 +99,7 @@ steps:
           *) echo "vault config: hard failure (rc=$rc)" >&2; exit "$rc" ;;
         esac
 
-  # ── 3. Shellcheck ────────────────────────────────────────────────────────
+  # ── 4. Shellcheck ────────────────────────────────────────────────────────
   # Covers the new lib/init/nomad/*.sh scripts plus bin/disinto (which owns
   # the backend dispatcher). bin/disinto has no .sh extension so the
   # repo-wide shellcheck in .woodpecker/ci.yml skips it — this step is the
@@ -91,7 +109,7 @@ steps:
     commands:
       - shellcheck --severity=warning lib/init/nomad/*.sh bin/disinto
 
-  # ── 4. bats: `disinto init --backend=nomad --dry-run` ────────────────────
+  # ── 5. bats: `disinto init --backend=nomad --dry-run` ────────────────────
   # Smoke-tests the CLI dispatcher: both --backend=nomad variants exit 0
   # with the expected step list, and --backend=docker stays on the docker
   # path (regression guard). Pure dry-run — no sudo, no network.

nomad/jobs/forgejo.nomad.hcl

@@ -0,0 +1,113 @@
+# =============================================================================
+# nomad/jobs/forgejo.nomad.hcl — Forgejo git server (Nomad service job)
+#
+# Part of the Nomad+Vault migration (S1.1, issue #840). First jobspec to
+# land under nomad/jobs/ — proves the docker driver + host_volume plumbing
+# from Step 0 (client.hcl) by running a real factory service.
+#
+# Host_volume contract:
+#   This job mounts the `forgejo-data` host_volume declared in
+#   nomad/client.hcl. That volume is backed by /srv/disinto/forgejo-data on
+#   the factory box, created by lib/init/nomad/cluster-up.sh before any job
+#   references it. Keep the `source = "forgejo-data"` below in sync with the
+#   host_volume stanza in client.hcl — drift = scheduling failures.
+#
+# No Vault integration yet — Step 2 (#...) templates in OAuth secrets and
+# replaces the inline FORGEJO__oauth2__* bits. The env vars below are the
+# subset of docker-compose.yml's forgejo service that does NOT depend on
+# secrets: DB type, public URL, install lock, registration lockdown, webhook
+# allow-list. OAuth app registration lands later, per-service.
+#
+# Not the runtime yet: docker-compose.yml is still the factory's live stack
+# until cutover. This file exists so CI can validate it and S1.3 can wire
+# `disinto init --backend=nomad --with forgejo` to `nomad job run` it.
+# =============================================================================
+
+job "forgejo" {
+  type        = "service"
+  datacenters = ["dc1"]
+
+  group "forgejo" {
+    count = 1
+
+    # Static :3000 matches docker-compose's published port so the rest of
+    # the factory (agents, woodpecker, caddy) keeps reaching forgejo at the
+    # same host:port during and after cutover. `to = 3000` maps the host
+    # port into the container's :3000 listener.
+    network {
+      port "http" {
+        static = 3000
+        to     = 3000
+      }
+    }
+
+    # Host-volume mount: declared in nomad/client.hcl, path
+    # /srv/disinto/forgejo-data on the factory box.
+    volume "forgejo-data" {
+      type      = "host"
+      source    = "forgejo-data"
+      read_only = false
+    }
+
+    # Conservative restart policy — fail fast to the scheduler instead of
+    # spinning on a broken image/config. 3 attempts over 5m, then back off.
+    restart {
+      attempts = 3
+      interval = "5m"
+      delay    = "15s"
+      mode     = "delay"
+    }
+
+    # Native Nomad service discovery (no Consul in this factory cluster).
+    # Health check gates the service as healthy only after the API is up;
+    # initial_status is deliberately unset so Nomad waits for the first
+    # probe to pass before marking the allocation healthy on boot.
+    service {
+      name     = "forgejo"
+      port     = "http"
+      provider = "nomad"
+
+      check {
+        type     = "http"
+        path     = "/api/v1/version"
+        interval = "10s"
+        timeout  = "3s"
+      }
+    }
+
+    task "forgejo" {
+      driver = "docker"
+
+      config {
+        image = "codeberg.org/forgejo/forgejo:11.0"
+        ports = ["http"]
+      }
+
+      volume_mount {
+        volume      = "forgejo-data"
+        destination = "/data"
+        read_only   = false
+      }
+
+      # Mirrors the non-secret env set from docker-compose.yml's forgejo
+      # service. OAuth/secret-bearing env vars land in Step 2 via Vault
+      # templates — do NOT add them here.
+      env {
+        FORGEJO__database__DB_TYPE             = "sqlite3"
+        FORGEJO__server__ROOT_URL              = "http://forgejo:3000/"
+        FORGEJO__server__HTTP_PORT             = "3000"
+        FORGEJO__security__INSTALL_LOCK        = "true"
+        FORGEJO__service__DISABLE_REGISTRATION = "true"
+        FORGEJO__webhook__ALLOWED_HOST_LIST    = "private"
+      }
+
+      # Baseline — tune once we have real usage numbers under nomad. The
+      # docker-compose stack runs forgejo uncapped; these limits exist so
+      # an unhealthy forgejo can't starve the rest of the node.
+      resources {
+        cpu    = 300
+        memory = 512
+      }
+    }
+  }
+}